Featuring synthetic RGBD video sequences of articulated objects derived from the PartNet-Mobility collection. It provides simulation data organized within a sim_data directory to facilitate the creation of interactable digital twins from casual video captures.
Use Cases
- Train computer vision models to identify articulation axes and part hierarchies using the RGBD frames.
- Benchmark digital twin reconstruction pipelines using the synthetic ground truth data in the sim_data directory.
- Develop pose estimation algorithms for articulated objects using the depth and color channels provided in the video sequences.
Strengths
- Derived from the PartNet-Mobility dataset, providing structured articulation data for 3D objects.
- Contains synthetic RGBD video sequences stored in a dedicated sim_data folder structure.
- Supports the iTACO paper's methodology for reconstructing interactable digital twins from casual captures.